Upload Qwen3ASRForConditionalGeneration
Browse files- config.json +35 -10
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -41,27 +41,52 @@
|
|
| 41 |
"hidden_size": 2048,
|
| 42 |
"initializer_range": 0.02,
|
| 43 |
"intermediate_size": 6144,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
"max_position_embeddings": 65536,
|
| 45 |
-
"
|
|
|
|
| 46 |
"num_attention_heads": 16,
|
| 47 |
"num_hidden_layers": 28,
|
| 48 |
"num_key_value_heads": 8,
|
| 49 |
"pad_token_id": null,
|
| 50 |
"rms_norm_eps": 1e-06,
|
| 51 |
"rope_parameters": {
|
| 52 |
-
"interleaved": true,
|
| 53 |
-
"mrope_interleaved": true,
|
| 54 |
-
"mrope_section": [
|
| 55 |
-
24,
|
| 56 |
-
20,
|
| 57 |
-
20
|
| 58 |
-
],
|
| 59 |
"rope_theta": 1000000,
|
| 60 |
-
"rope_type": "default"
|
| 61 |
-
"type": "default"
|
| 62 |
},
|
|
|
|
| 63 |
"tie_word_embeddings": true,
|
| 64 |
"use_cache": true,
|
|
|
|
| 65 |
"vocab_size": 151936
|
| 66 |
},
|
| 67 |
"transformers_version": "5.5.0.dev0"
|
|
|
|
| 41 |
"hidden_size": 2048,
|
| 42 |
"initializer_range": 0.02,
|
| 43 |
"intermediate_size": 6144,
|
| 44 |
+
"layer_types": [
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"full_attention",
|
| 55 |
+
"full_attention",
|
| 56 |
+
"full_attention",
|
| 57 |
+
"full_attention",
|
| 58 |
+
"full_attention",
|
| 59 |
+
"full_attention",
|
| 60 |
+
"full_attention",
|
| 61 |
+
"full_attention",
|
| 62 |
+
"full_attention",
|
| 63 |
+
"full_attention",
|
| 64 |
+
"full_attention",
|
| 65 |
+
"full_attention",
|
| 66 |
+
"full_attention",
|
| 67 |
+
"full_attention",
|
| 68 |
+
"full_attention",
|
| 69 |
+
"full_attention",
|
| 70 |
+
"full_attention",
|
| 71 |
+
"full_attention",
|
| 72 |
+
"full_attention"
|
| 73 |
+
],
|
| 74 |
"max_position_embeddings": 65536,
|
| 75 |
+
"max_window_layers": 28,
|
| 76 |
+
"model_type": "qwen3",
|
| 77 |
"num_attention_heads": 16,
|
| 78 |
"num_hidden_layers": 28,
|
| 79 |
"num_key_value_heads": 8,
|
| 80 |
"pad_token_id": null,
|
| 81 |
"rms_norm_eps": 1e-06,
|
| 82 |
"rope_parameters": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 83 |
"rope_theta": 1000000,
|
| 84 |
+
"rope_type": "default"
|
|
|
|
| 85 |
},
|
| 86 |
+
"sliding_window": null,
|
| 87 |
"tie_word_embeddings": true,
|
| 88 |
"use_cache": true,
|
| 89 |
+
"use_sliding_window": false,
|
| 90 |
"vocab_size": 151936
|
| 91 |
},
|
| 92 |
"transformers_version": "5.5.0.dev0"
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:361730b2a606a75eb9d495c5dc531b11337c0b59a68c7775d19e5094f90713e0
|
| 3 |
+
size 4076190632
|